[PATCH v2 1/2] vmsplice: unmap gifted pages for recipient

[Robert Jennings]

From: Robert C Jennings <rcj@xxxxxxxxxxxxxxxxxx>

Introduce use of the unused SPLICE_F_MOVE flag for vmsplice to zap
pages.

When vmsplice is called with flags (SPLICE_F_GIFT | SPLICE_F_MOVE) the
writer's gift'ed pages would be zapped.  This patch supports further work
to move vmsplice'd pages rather than copying them.  That patch has the
restriction that the page must not be mapped by the source for the move,
otherwise it will fall back to copying the page.

Signed-off-by: Matt Helsley <matt.helsley@xxxxxxxxx>
Signed-off-by: Robert C Jennings <rcj@xxxxxxxxxxxxxxxxxx>
---
Changes since v1:
 - Cleanup zap coalescing in splice_to_pipe for readability
 - Field added to struct partial_page in v1 was unnecessary, using 
   private field instead.
---
 fs/splice.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/fs/splice.c b/fs/splice.c
index 3b7ee65..c14be6f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -188,12 +188,18 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 {
 	unsigned int spd_pages = spd->nr_pages;
 	int ret, do_wakeup, page_nr;
+	struct vm_area_struct *vma;
+	unsigned long user_start, user_end, addr;
 
 	ret = 0;
 	do_wakeup = 0;
 	page_nr = 0;
+	vma = NULL;
+	user_start = user_end = 0;
 
 	pipe_lock(pipe);
+	/* mmap_sem taken for zap_page_range with SPLICE_F_MOVE */
+	down_read(&current->mm->mmap_sem);
 
 	for (;;) {
 		if (!pipe->readers) {
@@ -215,6 +221,33 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 			if (spd->flags & SPLICE_F_GIFT)
 				buf->flags |= PIPE_BUF_FLAG_GIFT;
 
+			/* Prepare to move page sized/aligned bufs.
+			 * Gather pages for a single zap_page_range()
+			 * call per VMA.
+			 */
+			if (spd->flags & (SPLICE_F_GIFT | SPLICE_F_MOVE) &&
+					!buf->offset &&
+					(buf->len == PAGE_SIZE)) {
+				addr = buf->private;
+
+				if (vma && (addr == user_end) &&
+					   (addr + PAGE_SIZE <= vma->vm_end)) {
+					/* Same vma, no holes */
+					user_end += PAGE_SIZE;
+				} else {
+					if (vma)
+						zap_page_range(vma, user_start,
+							(user_end - user_start),
+							NULL);
+					vma = find_vma(current->mm, addr);
+					if (!IS_ERR_OR_NULL(vma)) {
+						user_start = addr;
+						user_end = (addr + PAGE_SIZE);
+					} else
+						vma = NULL;
+				}
+			}
+
 			pipe->nrbufs++;
 			page_nr++;
 			ret += buf->len;
@@ -255,6 +288,10 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 		pipe->waiting_writers--;
 	}
 
+	if (vma)
+		zap_page_range(vma, user_start, (user_end - user_start), NULL);
+
+	up_read(&current->mm->mmap_sem);
 	pipe_unlock(pipe);
 
 	if (do_wakeup)
@@ -1475,6 +1512,7 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 
 			partial[buffers].offset = off;
 			partial[buffers].len = plen;
+			partial[buffers].private = (unsigned long)base;
 
 			off = 0;
 			len -= plen;
-- 
1.8.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/